OPENCV_TRAINCASCADE(1)

✨ NAME ✨

okay bestie, welcome to opencv_traincascade — the transcascade application 💖 (yes, that's what the manpage calls it, and honestly? iconic.) this page lives in section 1 of the manual, so when you see it written fancy it's OPENCV_TRAINCASCADE(1) 🎀

---

🌸 SYNOPSIS 🌸

opencv_traincascade [options]

that's it. that's the whole vibe. you just run it with some options and let it cook 🍓

---

🦋 DESCRIPTION 🦋

traincascade application. periodt. 💅

like, it trains cascades. that's the assignment. no cap.

---

👑 OPTIONS 👑

opencv_traincascade supports the following options:

💜 BASIC OPTIONS 💜

• -data cascade_dir_name — where the cascade directory lives, bestie
• -vec vec_file_name — the vec file name, hand it over
• -bg background_file_name — and the background file name too
• -numPos number_of_positive_samples — how many positive samples. the default is 2000.
• -numNeg number_of_negative_samples — how many negative samples. the default is 1000.
• -num Stagesnumber_of_stages — number of stages. the default is 20.
• -precalcValBufSize precalculated_vals_buffer_size_in_Mb — buffer size for precalculated vals, in Mb. the default is 256.
• -precalcIdxBufSize precalculated_idxs_buffer_size_in_Mb — buffer size for precalculated idxs, in Mb. the default is 256.
• -baseFormatSave — no description given, it's just there, mysterious main character energy 🫶

🌈 CASCADE OPTIONS 🌈

• -stageType — the default is BOOST.
• -featureType — set feature type. you can select HAAR or LBP. the default is HAAR.
• -w sampleWidth — the default is 24.
• -h sampleHeight — the default is 24.

🔥 BOOST OPTIONS 🔥

• -bt {DAB|RAB|LB|GAB} — the type of the applied boosting algorithm. you can choose between Discrete AdaBoost (DAB), Real AdaBoost (RAB), LogitBoost (LB) and Gentle AdaBoost (GAB). the default is GAB.
• -minHitRate min_hit_rate — the default is 0.995.
• -maxFalseAlarmRate max_false_alarm_rate — the default is 0.5.
• -weightTrimRate weight_trim_rate — the default is 0.95.
• -maxDepth max_depth_of_weak_tree — the default is 1.
• -maxWeakCount max_weak_tree_count — the default is 100.

🧚 HAARFEATURE OPTIONS 🧚

• -mode <BASIC|CORE|ALL> — the type of the applied haarFeature mode. you can choose between BASIC, ORE and ALL. the default is BASIC.

ok so heads up — the manpage literally says ORE there and not CORE, even though the option line above it lists CORE. i'm not touching it, i'm just telling you what it says, fr fr 🙈

---

💀 EXAMPLES 💀

TODO

not me being like... the examples section is literally just TODO 😭 the manpage said "i'll do it later" and never came back. leaving it exactly as found, bestie.

---

⭐ SEE ALSO ⭐

• opencv_haartraing(1) — yes that's spelled exactly like that on purpose, i promise i'm not being messy 💅
• opencv_performance(1)

more information and examples can be found in the OpenCV documentation. go read it, iykyk 📚✨

---

🎀 AUTHORS 🎀

this manual page was written by Nobuhiro Iwamatsu <iwamatsu@debian.org> for the Debian project (but may be used by others). slay, thank you for your service 🫶

---

and that's the whole page, bestie!! 💖 this one came from the OpenCV crew — version vibes from May 2010 — and it goes by OPENCV_TRAINCASCADE(1) in the manual lineup. take care of her, she's a legacy icon 👑✨🌸